EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transformer-Based Deep Learning for Population-Scale Retinal Image Screening of Ophthalmic Disorders

Wiem Abdelbaki iD, Wided Bouchelligua iD, Inzamam Mashood Nasir iD, Sara Tehsin iD, Hend Alshaya iD

Bioengineering · 25.03.2026 · 13 (4) · 377

DOI: 10.3390/bioengineering13040377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 25.03.2026. Verfasst von Wiem Abdelbaki und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Imam Mohammad ibn Saud Islamic University, Imam Mohammad ibn Saud Islamic University https://ror.org/05gxjyb39.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To perform screening of the retina on a population scale, an automated procedure is required that incorporates accurate, reproducible, interpretable, and computationally costeffective models. Existing approaches using convolutional or transformer architectures typically do not adequately represent both fine-grained pathology and large-scale retinal context simultaneously, which could adversely affect their reliability if used for large-scale applications in clinical practice. In this paper, we propose a hierarchical transformer-based screening framework for retinal fundus images that incorporates patch-based tokenization, global transformer encoding, and hierarchical aggregation of contextual information. We also developed a lightweight prediction head that supports screening for both single and multiple diseases. The framework has been evaluated using standard screening metrics, robustness, and cross-dataset generalization analyses on two eye retinopathy image databases: EyePACS and RFMiD. With regard to screening for a binary outcome of diabetic retinopathy, our method provided an accuracy of 89.4% and an area under the receiver operating characteristic (AUROC) curve of 93.6% on EyePACS and attained an accuracy of 95.2% and a macro-averaged F1 score of 82.7% on RFMiD. Our hierarchical transformer achieved improved robustness to degraded images and increased generalizability across datasets compared with all current state-of-the-art models. The proposed hierarchical transformer demonstrates strong potential for large-scale retinal screening and provides a promising foundation for future clinically validated deployment.

Schlagwörter

Stichwörter der Autor:innen

diabetic retinopathymedical image analysismulti-disease classificationpopulation-scale healthcareretinal image screeningvision transformers

Autor:innen und Institutionen

  • College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait.
  • Applied College, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia.
  • Human-Environment-Technology (HET) Systems Centre, Mykolas Romeris University, 08303 Vilnius, Lithuania.
  • Faculty of Informatics, Kaunas University of Technology, 51368 Kaunas, Lithuania.

ORCID-Profile: Wiem Abdelbaki, Wided Bouchelligua, Inzamam Mashood Nasir, Sara Tehsin, Hend Alshaya

Förderung

  • Imam Mohammad ibn Saud Islamic University
  • Imam Mohammad ibn Saud Islamic University https://ror.org/05gxjyb39

Zitieren

APA

Abdelbaki, W., Bouchelligua, W., Nasir, I. M., Tehsin, S., & Alshaya, H. (2026). Transformer-Based Deep Learning for Population-Scale Retinal Image Screening of Ophthalmic Disorders. Bioengineering, 13(4), 377. https://doi.org/10.3390/bioengineering13040377

Vancouver

Abdelbaki W, Bouchelligua W, Nasir IM, Tehsin S, Alshaya H. Transformer-Based Deep Learning for Population-Scale Retinal Image Screening of Ophthalmic Disorders. Bioengineering. 2026;13(4):377. doi:10.3390/bioengineering13040377

BibTeX
@article{Abdelbaki2026,
  author = {Abdelbaki, Wiem and Bouchelligua, Wided and Nasir, Inzamam Mashood and Tehsin, Sara and Alshaya, Hend},
  title = {Transformer-Based Deep Learning for Population-Scale Retinal Image Screening of Ophthalmic Disorders},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {377},
  doi = {10.3390/bioengineering13040377}
}
Kostenlos starten →